Text Change Detection in Multilingual Documents Using Image Comparison

TL;DR

This paper introduces a novel image comparison approach for detecting text changes in multilingual documents, bypassing OCR limitations and improving accuracy across diverse languages.

Contribution

It presents a word-level image comparison model with multi-scale attention features for multilingual text change detection, along with a new benchmark dataset.

Findings

Outperforms OCR-based methods in multilingual scenarios

Effective change segmentation without explicit text alignment

Validated on multiple datasets including a new benchmark

Abstract

Document comparison typically relies on optical character recognition (OCR) as its core technology. However, OCR requires the selection of appropriate language models for each document and the performance of multilingual or hybrid models remains limited. To overcome these challenges, we propose text change detection (TCD) using an image comparison model tailored for multilingual documents. Unlike OCR-based approaches, our method employs word-level text image-to-image comparison to detect changes. Our model generates bidirectional change segmentation maps between the source and target documents. To enhance performance without requiring explicit text alignment or scaling preprocessing, we employ correlations among multi-scale attention features. We also construct a benchmark dataset comprising actual printed and scanned word pairs in various languages to evaluate our model. We validate our approach using our benchmark dataset and public benchmarks Distorted Document Images and the LRDE Document Binarization Dataset. We compare our model against state-of-the-art semantic segmentation and change detection models, as well as to conventional OCR-based models.